Skip to main content
3 votes

Do all expert trajectories have the same starting state in apprenticeship learning?

All right, I figured it out. trajectories need not have the same starting state because the distribution of $s_0$ is drawn from a distribution D (mentioned in the paper). Had been confused because ...
calveeen's user avatar
  • 1,281
3 votes

In imitation learning, do you simply inject optimal tuples of experience $(s, a, r, s')$ into your experience replay buffer?

That seems to be functional. That is a great approach, as long as you are using an off-policy algorithm (since the samples you are using to learn are not the policy currently being performed), like Q-...
BlueMoon93's user avatar
2 votes

What does the notation ${s'\sim T(s,a,\cdot)}$ mean?

The dot ($.$) at the end of $T(s,a,.)$ shows all possible states that we can go from state $S$ by doing action $a$. As you know there are some probabilities here for choosing those states, that the ...
OmG's user avatar
  • 1,826
1 vote

What does the number of required expert demonstrations in Imitation Learning depend on?

The answer to your question can be found in the original paper that introduced the max-margin and projection imitation learning (IL) algorithms: Apprenticeship Learning via Inverse Reinforcement ...
nbro's user avatar
  • 40.9k

Only top scored, non community-wiki answers of a minimum length are eligible